Fund backflow detection method and device, computer equipment, medium and program product

Abstract

The invention relates to a fund backflow detection method and device, computer equipment, a medium and a program product, and belongs to the technical field of big data. The method comprises the steps that transaction data corresponding to a target user to be subjected to fund backflow detection is acquired, transaction time sequence data and an adjacent matrix of a transaction directed graph are acquired according to the transaction data, and the transaction users comprise the target user and users having fund exchange with the target user; inputting the adjacent matrix into a pre-trained graph attention neural network model, and obtaining an intermediate matrix based on the output of the graph attention neural network model; the transaction time sequence data is converted based on the intermediate matrix, multiple vectors obtained after conversion are input into a pre-trained time sequence neural network model, the time sequence neural network model outputs indication information, and the indication information is used for indicating whether fund backflow exists in the target user or not. By adopting the method, whether fund backflow exists in the target user or not can be automatically detected.

Description

technical field [0001] The present application relates to the field of big data technology, and in particular to a fund backflow detection method, device, computer equipment, media and program products. Background technique [0002] In the case of a user borrowing from a bank, in order to ensure the safety of the bank's loan funds, the bank usually requires the user to promise the use of the borrowed funds. At the same time, the bank will test the use of the funds borrowed by the user to see if there is a return of funds. Among them, the return of funds means that the customer uses the borrowed funds for purposes that are not what they promised. In the prior art, the phenomenon of capital return is mainly detected manually, but the intelligence of manually detecting the phenomenon of capital return is not high. Contents of the invention [0003] Based on this, it is necessary to provide a fund backflow detection method, device, computer equipment, media and program produc...

AI Technical Summary

Problems solved by technology

In the prior art, the phenomenon of capital return is mainly detected manually, but the intelligence of manually detecting the phenomenon of capital return is not high

Images